Triple
T20202620
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brunnsviken |
E493261
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Frescati area |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Frescati area | Statement: [Brunnsviken, adjacentTo, Frescati area]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frescati area Context triple: [Brunnsviken, adjacentTo, Frescati area]
-
A.
Frescati
chosen
Frescati is an area in northern Stockholm, Sweden, known for hosting Stockholm University and several major cultural and scientific institutions.
-
B.
Pallavicini area
The Pallavicini area is a famously steep and challenging expert terrain zone at Colorado’s Arapahoe Basin Ski Area, known for its moguls, trees, and advanced runs.
-
C.
Canosa di Puglia
Canosa di Puglia is a historic town in the Apulia region of southern Italy, known for its ancient archaeological heritage and medieval monuments.
-
D.
Alta Rocca region
The Alta Rocca region is a mountainous area in southern Corsica known for its dramatic granite peaks, dense forests, and traditional hilltop villages.
-
E.
Fuorigrotta district
Fuorigrotta district is a populous western neighborhood of Naples, Italy, known for its major sports venues, trade fair grounds, and busy commercial streets.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69da6269614c8190bb40475d9d477358 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66d8ec73c8190b630599c5ceb22ac |
completed | April 20, 2026, 6:16 p.m. |
Created at: April 11, 2026, 11:37 p.m.